Leveraging Taxonomy and LLMs for Improved Multimodal Hierarchical Classification
This addresses inconsistent predictions in hierarchical classification for e-commerce product categorization, but it appears incremental as it builds on existing LLM methods.
The paper tackled the problem of inconsistent predictions in multi-level hierarchical classification by proposing a taxonomy-embedded framework using LLMs, resulting in significant performance improvements on the MEP-3M dataset.
Multi-level Hierarchical Classification (MLHC) tackles the challenge of categorizing items within a complex, multi-layered class structure. However, traditional MLHC classifiers often rely on a backbone model with independent output layers, which tend to ignore the hierarchical relationships between classes. This oversight can lead to inconsistent predictions that violate the underlying taxonomy. Leveraging Large Language Models (LLMs), we propose a novel taxonomy-embedded transitional LLM-agnostic framework for multimodality classification. The cornerstone of this advancement is the ability of models to enforce consistency across hierarchical levels. Our evaluations on the MEP-3M dataset - a multi-modal e-commerce product dataset with various hierarchical levels - demonstrated a significant performance improvement compared to conventional LLM structures.